End-to-End Variational Networks for Accelerated MRI Reconstruction
Anuroop Sriram, Jure Zbontar, Tullie Murrell, Aaron Defazio, C. Lawrence Zitnick, Nafissa Yakubova, Florian Knoll, Patricia Johnson
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/facebookresearch/fastMRIOfficialIn paperpytorch★ 1,513
- github.com/z-fabian/MRAugmentpytorch★ 31
- github.com/MathFLDS/MRAugmentpytorch★ 13
Abstract
The slow acquisition speed of magnetic resonance imaging (MRI) has led to the development of two complementary methods: acquiring multiple views of the anatomy simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing). While the combination of these methods has the potential to allow much faster scan times, reconstruction from such undersampled multi-coil data has remained an open problem. In this paper, we present a new approach to this problem that extends previously proposed variational methods by learning fully end-to-end. Our method obtains new state-of-the-art results on the fastMRI dataset for both brain and knee MRIs.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| fastMRI Brain 4x | End-to-end variational network | SSIM | 0.96 | — | Unverified |
| fastMRI Brain 8x | End-to-end variational network | SSIM | 0.94 | — | Unverified |
| fastMRI Knee 4x | End-to-end variational network | SSIM | 0.93 | — | Unverified |
| fastMRI Knee 8x | End-to-end variational network | SSIM | 0.89 | — | Unverified |
| fastMRI Knee Val 8x | E2E-VarNet (train+val) | SSIM | 0.89 | — | Unverified |